Cerber — AI skill for Claude Code
AI code-review cockpit: Claude reviews PRs into local artifacts; nothing reaches GitHub until you say so.
How to install Cerber
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open fullstackhouse/cerber and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Cerber does
AI code-review cockpit: Claude reviews PRs into local artifacts; nothing reaches GitHub until you say so.
Alternatives in AI
- Omniget — Udemy & Hotmart course downloader, YouTube downloader (yt-dlp GUI, 1,800+ sites) + desktop app for AI agents 13.9k ★
- Ralph For Claude Code — by Frank Bria - An autonomous AI development framework that enables Claude Code to work iteratively on project 8k ★
- Ralph Loop — A long-running AI agent loop 292 ★
README
cerber 🐕
[](https://www.npmjs.com/package/@fullstackhouse/cerber) [](https://github.com/fullstackhouse/cerber/actions/workflows/ci.yml) [](./LICENSE)
**AI code-review cockpit.** Claude reviews your pull requests into local artifacts — a summary, a chaptered walkthrough of the changes, draft inline comments, and a verdict with a confidence score. You read it in a local web cockpit, keep or rewrite or drop each comment, then press Send when you agree with it.
**Nothing reaches GitHub until you explicitly say so.** Reviewing is 100% local and read-only; three things can write, each one a click you make — the Send button, opt-in daemon auto-send you turn on yourself, and handing a review to somebody else. A review only ever goes out under your own account because you decided it should: Send posts the one you vouched for, and a handoff posts the draft only if you ticked the box to send it along, always as a comment.
That gate is the whole point, and the reason this is not another review bot:
Reviewing pull requests with an AI model creates a specific danger: a system that can both draft opinions and hold GitHub credentials will eventually post one without a human deciding it should.
Named after Cerberus, the gatekeeper: cerber guards what gets merged.
Why it exists, and the four things I tried first: [AI drafts the review. I decide what gets sent.](https://www.fullstack.house/blog/cerber?utm_source=github&utm_medium=readme)
**The whole loop in seventeen seconds** — five PRs already drafted when you sit down, the one that isn't an approval, straight to its blocker, arguing with the reviewer until it rewrites its own finding, dropping the comment you disagree with, and sending what's left as your review:
![The cockpit: an inbox of five drafted reviews; open
Related Skills
Multi Agent Review
Claude Code reviews PRs made by Codex and other AI agents — like CodeRabbit, but agent-to-agent
Grand Tour
A Claude skill that tours a codebase you built with AI until you can explain how it works: traces one real run
Unterm
The terminal AI agents can drive — and the cockpit to run them from. 99 MCP methods / 21 namespaces, agent Inb
Acp Cockpit
A browser client for AI coding agents that speaks the Agent Client Protocol directly — no terminal, no TUI, no
Raptors Install
Release the raptors (AI dev agents + pipelines) into the current project's .claude/ directory. Opt-in per repo
Mangchi
Iterative cross-model code refinement - Claude edits, Codex reviews one axis at a time with verification loop,
Related Agents
Orbit Code Reviewer
Senior. Skeptical. Reviews PRs critically, blocks bad code, demands tests. Final say on code quality before me
Compass Planner
Use this agent when the user needs a structured work plan from a vague idea, when they say 'plan this' or 'let
Dead Code
Confirms what nothing reaches — unreferenced exports, files, and dependencies from the tool receipts, plus wha